{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.0573031902313232, "min": 1.0283350944519043, "max": 1.482879400253296, "count": 10 }, "Pyramids.Policy.Entropy.sum": { "value": 31668.345703125, "min": 31031.041015625, "max": 44984.62890625, "count": 10 }, "Pyramids.Step.mean": { "value": 299877.0, "min": 29952.0, "max": 299877.0, "count": 10 }, "Pyramids.Step.sum": { "value": 299877.0, "min": 29952.0, "max": 299877.0, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05917356163263321, "min": -0.25081866979599, "max": -0.03742930665612221, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -14.260828018188477, "min": -59.44402313232422, "max": -9.095321655273438, "count": 10 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.030130205675959587, "min": 0.030130205675959587, "max": 0.7908480763435364, "count": 10 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.261379718780518, "min": 7.261379718780518, "max": 187.43099975585938, "count": 10 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06475406583659439, "min": 0.06475406583659439, "max": 0.07585369387313903, "count": 10 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9065569217123215, "min": 0.5309758571119733, "max": 0.9974047183231861, "count": 10 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.001817064645193388, "min": 0.001050950420061226, "max": 0.024435870466820126, "count": 10 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.025438905032707432, "min": 0.014036133841501245, "max": 0.17105109326774087, "count": 10 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00021437231425685716, "min": 0.00021437231425685716, "max": 0.00029515063018788575, "count": 10 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0030012123995960004, "min": 0.0020660544113152, "max": 0.0037574359475213994, "count": 10 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1714574285714286, "min": 0.1714574285714286, "max": 0.19838354285714285, "count": 10 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.4004040000000004, "min": 1.3886848, "max": 2.6524786, "count": 10 }, "Pyramids.Policy.Beta.mean": { "value": 0.007148597114285714, "min": 0.007148597114285714, "max": 0.00983851593142857, "count": 10 }, "Pyramids.Policy.Beta.sum": { "value": 0.1000803596, "min": 0.06886961152, "max": 0.12526261214, "count": 10 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.03676452115178108, "min": 0.03676452115178108, "max": 0.8733783960342407, "count": 10 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.5147032737731934, "min": 0.5147032737731934, "max": 6.113648891448975, "count": 10 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 962.5862068965517, "min": 885.1351351351351, "max": 999.0, "count": 10 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27915.0, "min": 15984.0, "max": 32750.0, "count": 10 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.6872483227273514, "min": -1.0000000521540642, "max": -0.3992054512774622, "count": 10 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -19.93020135909319, "min": -30.35600170493126, "max": -14.770601697266102, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.6872483227273514, "min": -1.0000000521540642, "max": -0.3992054512774622, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -19.93020135909319, "min": -30.35600170493126, "max": -14.770601697266102, "count": 10 }, "Pyramids.Policy.RndReward.mean": { "value": 0.386942556641739, "min": 0.386942556641739, "max": 19.006777239963412, "count": 10 }, "Pyramids.Policy.RndReward.sum": { "value": 11.22133414261043, "min": 10.600268902257085, "max": 304.1084358394146, "count": 10 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688465285", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1688465899" }, "total": 614.7416767500004, "count": 1, "self": 0.8938760790001652, "children": { "run_training.setup": { "total": 0.04016198900035306, "count": 1, "self": 0.04016198900035306 }, "TrainerController.start_learning": { "total": 613.8076386819998, "count": 1, "self": 0.4007816530020136, "children": { "TrainerController._reset_env": { "total": 3.9895837120002398, "count": 1, "self": 3.9895837120002398 }, "TrainerController.advance": { "total": 609.4130555079978, "count": 20147, "self": 0.4298157931143578, "children": { "env_step": { "total": 411.5424404559358, "count": 20147, "self": 377.7109921189153, "children": { "SubprocessEnvManager._take_step": { "total": 33.599505514002885, "count": 20147, "self": 1.446341112995924, "children": { "TorchPolicy.evaluate": { "total": 32.15316440100696, "count": 20000, "self": 32.15316440100696 } } }, "workers": { "total": 0.23194282301756175, "count": 20147, "self": 0.0, "children": { "worker_root": { "total": 612.3738449340262, "count": 20147, "is_parallel": true, "self": 268.73282553302124, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017753709998942213, "count": 1, "is_parallel": true, "self": 0.0005532139998649654, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012221570000292559, "count": 8, "is_parallel": true, "self": 0.0012221570000292559 } } }, "UnityEnvironment.step": { "total": 0.05116309300001376, "count": 1, "is_parallel": true, "self": 0.0006325649997052096, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048526199998377706, "count": 1, "is_parallel": true, "self": 0.00048526199998377706 }, "communicator.exchange": { "total": 0.04762792600013199, "count": 1, "is_parallel": true, "self": 0.04762792600013199 }, "steps_from_proto": { "total": 0.0024173400001927803, "count": 1, "is_parallel": true, "self": 0.00039833900018493296, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020190010000078473, "count": 8, "is_parallel": true, "self": 0.0020190010000078473 } } } } } } }, "UnityEnvironment.step": { "total": 343.641019401005, "count": 20146, "is_parallel": true, "self": 10.434304075012278, "children": { "UnityEnvironment._generate_step_input": { "total": 7.09531802002266, "count": 20146, "is_parallel": true, "self": 7.09531802002266 }, "communicator.exchange": { "total": 295.03710324501435, "count": 20146, "is_parallel": true, "self": 295.03710324501435 }, "steps_from_proto": { "total": 31.074294060955708, "count": 20146, "is_parallel": true, "self": 5.978077508113074, "children": { "_process_rank_one_or_two_observation": { "total": 25.096216552842634, "count": 161168, "is_parallel": true, "self": 25.096216552842634 } } } } } } } } } } }, "trainer_advance": { "total": 197.44079925894766, "count": 20147, "self": 0.6584265248916381, "children": { "process_trajectory": { "total": 32.6256177480559, "count": 20147, "self": 32.6256177480559 }, "_update_policy": { "total": 164.15675498600012, "count": 132, "self": 105.16791346599894, "children": { "TorchPPOOptimizer.update": { "total": 58.98884152000119, "count": 7248, "self": 58.98884152000119 } } } } } } }, "trainer_threads": { "total": 1.1299998732283711e-06, "count": 1, "self": 1.1299998732283711e-06 }, "TrainerController._save_models": { "total": 0.004216678999910073, "count": 1, "self": 2.296999991813209e-05, "children": { "RLTrainer._checkpoint": { "total": 0.004193708999991941, "count": 1, "self": 0.004193708999991941 } } } } } } }